Reading list of online hate detection

Online Hate Detection

• Characterizing and Detecting Hateful Users on Twitter
• The Risk of Racial Bias in Hate Speech Detection
• Automated Hate Speech Detection and the Problem of Offensive Language
• Detecting the Hate Code on Social Media
• Hate Lingo: A Target-Based Linguistic Analysis of Hate Speech in Social Media
• Learning to Decipher Hate Symbols
• Analyzing the Targets of Hate in Online Social Media
• Characterizing and Detecting Hateful Users on Twitter
• Peer to Peer Hate: Hate Speech Instigators and Their Targets
• Spread of Hate Speech in Online Social Media
• Mobilizing the Trump Train: Understanding Collective Action in a Political Trolling Community
• A Benchmark Dataset for Learning to Intervene in Online Hate Speech
• Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations
• The Risk of Racial Bias in Hate Speech Detection

Adversarial Text

• TEXTBUGGER: Generating Adversarial Text Against Real-world Applications
• Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency
• GENERATING NATURAL ADVERSARIAL EXAMPLES
• Combating Adversarial Misspellings with Robust Word Recognition
• Generating Natural Language Adversarial Examples
• NATURAL LANGUAGE ADVERSARIAL ATTACKS AND DEFENSES IN WORD LEVEL
• Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey
• Analysis Methods in Neural Language Processing: A Survey
• Adversarial NAACL 2019
• Natural Adversarial Examples
• FREELB: ENHANCED ADVERSARIAL TRAINING FOR LANGUAGE UNDERSTANDING
• Adversarial Training for Free!
• You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
• Reading Thieves Cant: Automatically Identifying and Understanding Dark Jargons from Cybercrime Marketplaces
• Generating Text via Adversarial Training
• GANS for Sequences of Discrete Elements with the Gumbel-softmax Distribution
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
• Defending Neural Backdoors via Generative Distribution Modeling
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• Adversarial Examples for Evaluating Reading Comprehension Systems
• A Survey: Towards a Robust Deep Neural Network in Text Domain
• TextFool: Fool your Model with Natural Adversarial Text
• Universal Adversarial Perturbation for Text Classification
• Towards Robust Toxic Content Classification
• Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment
• Deep Text Classification Can be Fooled
• Adversarial Attacks and Defenses in Images, Graphs and Text: A Review
• Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples
• Universal Adversarial Triggers for Attacking and Analyzing NLP
• ADVCODEC: TOWARDS A UNIFIED FRAMEWORK FOR ADVERSARIAL TEXT GENERATION
• DETECTING EGREGIOUS RESPONSES IN NEURAL SEQUENCE-TO-SEQUENCE MODELS
• Say What I Want: Towards the Dark Side of Neural Dialogue Models
• Finding Social Media Trolls: Dynamic Keyword Selection Methods for Rapidly-Evolving Online Debates
• Must-read Papers on Textual Adversarial Attack and Defense (TAAD)
• On the Robustness of Self-Attentive Models
• How the Embedding Layers in BERT Were Implemented
• TEXTSHIELD: Robust Text Classification Based on Multimodal Embedding and Neural Machine Translation
• Hidden resilience and adaptive dynamics of the global online hate ecology
• Defending Against Neural Fake News
• MIT CSAIL’s TextFooler generates adversarial text to strengthen natural language models
• Towards Robust Toxic Content Classification
• Defending Neural Backdoors via Generative Distribution Modeling
• Say What I Want: Towards the Dark Side of Neural Dialogue Models
• CNN-generated images are surprisingly easy to spot... for now
• Multi-Modal Sarcasm Detection in Twitter with Hierarchical Fusion Model
• Towards Multimodal Sarcasm Detection (An Obviously Perfect Paper)
• Exploring Hate Speech Detection in Multimodal Publications
• Exploring Deep Multimodal Fusion of Text and Photo for Hate Speech Classification
• Generating Counter Narratives against Online Hate Speech: Data and Strategies
• Attend and Attack: Attention Guided Adversarial Attacks on Visual Question Answering Models
• Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning
• Fooling Vision and Language Models Despite Localization and Attention Mechanism
• Adversarial Training and Robustness for Multiple Perturbations
• Awesome Multimodal ML
• A Survey of Black-Box Adversarial Attacks on Computer Vision Models

Adversarial Examples

• Adversarial examples: Attacks and defenses for deep learning
• On Evaluating Adversarial Robustness
• Adversarial Examples Are Not Bugs, They Are Features
• Deepsec: A uniform platform for security analysis of deep learning model
• Adversarial training and robustness for multiple perturbations
• On adaptive attacks to adversarial example defenses
• Benchmarking Adversarial Robustness
• Adversarial attacks and defenses in images, graphs and text: A review
• Towards a Robust Deep Neural Network in Texts: A Survey
• Textual Adversarial Attack and Defense Reading List

Multimodal Adversarial Attacks

• Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
• What are you talking about? Text-to-Image Coreference
• Attend and Attack: Attention Guided Adversarial Attacks on Visual Question Answering Models
• Tutorial on Multimodal Machine Learning
• Fooling Vision and Language Models Despite Localization and Attention Mechanism
• Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables

Useful Models

• Deep Anomaly Detection on Attributed Networks

Papers on Graph Convolutional Networks (GCNs)

• Spam Review Detection with Graph Convolutional Networks
• Exploring Visual Relationship for Image Captioning
• Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
• Relational inductive biases, deep learning, and graph networks
• Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations
• Deep Anomaly Detection on Attributed Networks
• The Risk of Racial Bias in Hate Speech Detection
• What Do We Understand About Convolutional Networks?
• Order Matters: Semantic-Aware Neural Networks for Binary Code Similarity Detection

Papers/Articles on Memes

• Living the Meme: AI as Funny as Humans for Generating Image Captions
• Memeify: A Large-Scale Meme Generation System
• SimMeme: A Search Engine for Internet Memes
• On the Origins of Memes by Means of Fringe Web Communities

Other Interesting Papers

• NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations
• PI-Bully: Personalized Cyberbullying Detection with Peer Influence
• Fairness in Deep Learning: A Computational Perspective
• “I am uncomfortable sharing what I can’t see”: Privacy Concerns of the Visually Impaired with Camera Based Assistive Applications
• Techniques for Interpretable Machine Learning